Successive Quantization of the Neural Network Equalizers in Optical Fiber Communication - Equipe Télécommunications Optiques Access content directly
Conference Papers Year : 2023

Successive Quantization of the Neural Network Equalizers in Optical Fiber Communication

Nelson Costa
  • Function : Author
  • PersonId : 1257026
Antonio Napoli
  • Function : Author
  • PersonId : 1257027
Jaoa Pedro
  • Function : Author
  • PersonId : 1096217

Abstract

pragmatic successive quantization approach is applied to a neural network equalizer in a 16-QAM dualpolarization fiber transmission experiment over a 9x50km TWC fiber link. Quantization at 5 bits reduces the complexity by 85%, with a negligible Q-factor penalty
Fichier principal
Vignette du fichier
Darweesh OECC2023.pdf (437.37 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-04252904 , version 1 (21-10-2023)

Identifiers

  • HAL Id : hal-04252904 , version 1

Cite

Jamal Darweesh, Nelson Costa, Yves Jaouën, Antonio Napoli, Jaoa Pedro, et al.. Successive Quantization of the Neural Network Equalizers in Optical Fiber Communication. OptoElectronics and Communications Conference OECC 2023, Jul 2023, Shanghai, China. ⟨hal-04252904⟩
26 View
10 Download

Share

Gmail Facebook X LinkedIn More